Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 14 hours
Course Outline
Introduction
- Distinguishing between workflows and autonomous agents
- High-level architecture and common application scenarios
Core Concepts of the Claude API
- Messages API, model selection, and parameter configuration
- System prompts and generating structured outputs
- Implementing streaming and managing errors
- Practical session: Initial API integration
Implementing Tool Usage
- Specifying tools and defining schemas
- The tool-invocation cycle and strategies for error recovery
- Practical session: Creating an agent that interacts with internal company APIs
MCP and Agent Skills
- Understanding MCP servers and clients
- Leveraging existing servers and developing a basic custom server
- Utilizing Agent Skills to encapsulate reusable capabilities
- Practical session: Connecting an agent to an external data source
Utilizing the Claude Agent SDK
- Managing the agent loop, sessions, and context
- Configuring permissions, hooks, and subagents
- Practical session: Developing an agent for research and reporting tasks
Optimizing Cost, Quality, and Safety
- Implementing prompt caching and managing token budgets
- Establishing guardrails and human-in-the-loop approval processes
- Running evaluations using a small test dataset
- Logging and monitoring operations
Transitioning from Prototype to Production
- Exploring deployment strategies and secure secret management
- Long-term maintenance and version control
- Developing a roadmap for participants' specific use cases
Requirements
- Proficiency in Python or TypeScript programming
- Familiarity with REST API integration and JSON processing
- Fundamental knowledge of large language models
Target Audience
- Software engineers and data specialists integrating AI capabilities into products and internal systems
- Architects assessing agent-based solutions
- Technical teams aiming to transition from experimental prototypes to production-ready systems
Testimonials (3)
The trainer is patient and very helpful. He knows the topic well.
CLIFFORD TABARES - Universal Leaf Philippines, Inc.
Course - Agentic AI for Business Automation: Use Cases & Integration
Good mixvof knowledge and practice
Ion Mironescu - Facultatea S.A.I.A.P.M.
Course - Agentic AI for Enterprise Applications
The mix of theory and practice and of high level and low level perspectives
